{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T22:31:08Z","timestamp":1781130668560,"version":"3.54.1"},"posted":{"date-parts":[[2024,9,11]]},"group-title":"Bioinformatics","reference-count":27,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,9,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Cryogenic Electron Microscopy (cryo-EM) is a core experimental technique used to determine the structure of macromolecules such as proteins. However, the effectiveness of cryo-EM is often hindered by the noise and missing density values in cryo-EM density maps caused by experimental conditions such as low contrast and conformational heterogeneity. Although various global and local map sharpening techniques are widely employed to improve cryo-EM density maps, it is still challenging to efficiently improve their quality for building better protein structures from them.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    In this study, we introduce CryoTEN - a three-dimensional U-Net style transformer to improve cryo-EM maps effectively. CryoTEN is trained using a diverse set of 1,295 cryo-EM maps as inputs and their corresponding simulated maps generated from known protein structures as targets. An independent test set containing 150 maps is used to evaluate CryoTEN, and the results demonstrate that it can robustly enhance the quality of cryo-EM density maps. In addition, the automatic de novo protein structure modeling shows that the protein structures built from the density maps processed by CryoTEN have substantially better quality than those built from the original maps. Compared to the existing state- of-the-art deep learning methods for enhancing cryo-EM density maps, CryoTEN ranks second in improving the quality of density maps, while running\n                    <jats:italic>&gt;<\/jats:italic>\n                    10 times faster and requiring much less GPU memory than them.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>\n                    The source code and data is freely available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jianlin-cheng\/cryoten\">https:\/\/github.com\/jianlin-cheng\/cryoten<\/jats:ext-link>\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2024.09.06.611715","type":"posted-content","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T14:40:16Z","timestamp":1726065616000},"source":"Crossref","is-referenced-by-count":4,"title":["CryoTEN: Efficiently Enhancing Cryo-EM Density Maps Using Transformers"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0068-3262","authenticated-orcid":false,"given":"Joel","family":"Selvaraj","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0305-2853","authenticated-orcid":false,"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"issue":"Pt 9","key":"2024091522252106000_2024.09.06.611715v1.1","first-page":"814","article-title":"New tools for the analysis and validation of cryo-EM maps and atomic models","volume":"74","year":"2018","journal-title":"Acta Crystallogr. D Struct. Biol"},{"key":"2024091522252106000_2024.09.06.611715v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18952-1"},{"key":"2024091522252106000_2024.09.06.611715v1.3","doi-asserted-by":"publisher","DOI":"10.20944\/preprints202408.1936.v2"},{"key":"2024091522252106000_2024.09.06.611715v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae109"},{"key":"2024091522252106000_2024.09.06.611715v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2009.07.008"},{"key":"2024091522252106000_2024.09.06.611715v1.6","doi-asserted-by":"crossref","unstructured":"N. Giri and J. Cheng . De novo atomic protein structure modeling for cryo-EM density maps using 3D transformer and hidden markov model. bioRxivorg, Jan. 2024a.","DOI":"10.1101\/2024.01.02.573943"},{"issue":"1","key":"2024091522252106000_2024.09.06.611715v1.7","doi-asserted-by":"crossref","first-page":"5511","DOI":"10.1038\/s41467-024-49647-6","article-title":"De novo atomic protein structure modeling for cryoem density maps using 3d transformer and hmm","volume":"15","year":"2024","journal-title":"Nature Communications"},{"key":"2024091522252106000_2024.09.06.611715v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae282"},{"key":"2024091522252106000_2024.09.06.611715v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39031-1"},{"key":"2024091522252106000_2024.09.06.611715v1.10","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.27131"},{"issue":"1","key":"2024091522252106000_2024.09.06.611715v1.11","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1038\/s41467-021-21509-5","article-title":"Local computational methods to improve the interpretability and analysis of cryo-EM maps","volume":"12","year":"2021","journal-title":"Nat. Commun"},{"key":"2024091522252106000_2024.09.06.611715v1.12","doi-asserted-by":"publisher","DOI":"10.1107\/S2059798319011471"},{"key":"2024091522252106000_2024.09.06.611715v1.13","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.20084"},{"key":"2024091522252106000_2024.09.06.611715v1.14","doi-asserted-by":"publisher","DOI":"10.1002\/pro.3943"},{"key":"2024091522252106000_2024.09.06.611715v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-0731-1"},{"key":"2024091522252106000_2024.09.06.611715v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4169"},{"key":"2024091522252106000_2024.09.06.611715v1.17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz671"},{"key":"2024091522252106000_2024.09.06.611715v1.18","doi-asserted-by":"crossref","unstructured":"O. Ronneberger , P. Fischer , and T. Brox . U-net: Convolutional networks for biomedical image segmentation. In N. Navab , J. Hornegger , W. M. Wells , and A. F. Frangi , editors, Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015, pages 234\u2013241, Cham, 2015. Springer International Publishing. ISBN 978-3-319-24574-4.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2024091522252106000_2024.09.06.611715v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2003.07.013"},{"key":"2024091522252106000_2024.09.06.611715v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02399-1"},{"key":"2024091522252106000_2024.09.06.611715v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2011.11.010"},{"key":"2024091522252106000_2024.09.06.611715v1.22","year":"2022","journal-title":"Unetr++: Delving into efficient and accurate 3d medical image segmentation"},{"key":"2024091522252106000_2024.09.06.611715v1.23","doi-asserted-by":"crossref","unstructured":"G. Terashi and D. Kihara . De novo main-chain modeling for EM maps using MAINMAST. Nat. Commun., 9(1), Dec. 2018.","DOI":"10.1038\/s41467-018-04053-7"},{"key":"2024091522252106000_2024.09.06.611715v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0173-1"},{"key":"2024091522252106000_2024.09.06.611715v1.25","doi-asserted-by":"publisher","DOI":"10.1107\/S2059798318004655"},{"issue":"6","key":"2024091522252106000_2024.09.06.611715v1.26","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1007\/s11633-023-1466-0","article-title":"Practical blind image denoising via swin-conv-UNet and data synthesis","volume":"20","year":"2023","journal-title":"Mach. Intell. Res"},{"key":"2024091522252106000_2024.09.06.611715v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01049-4"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.09.06.611715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:01:40Z","timestamp":1768460500000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2024.09.06.611715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1101\/2024.09.06.611715","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1093\/bioinformatics\/btaf092","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,9,11]]},"subtype":"preprint"}}